Method for evaluating driving behavior, computer program product, device and storage medium

Abstract

The application relates to a driving behavior evaluation method, a computer program product, equipment and a storage medium, comprising: obtaining time-labeled driving data of a target vehicle; dividing the driving data into multiple segments according to a preset time period, and respectively counting road condition characteristic data and driving style characteristic data of each segment according to the driving data; respectively determining a corresponding road condition, a frequency weight of the road condition and an evaluation weight of the road condition of each segment according to the road condition characteristic data; respectively determining a corresponding driving style of each segment according to the driving style characteristic data; and obtaining a driving behavior evaluation result of the target vehicle based on a preset basic score corresponding to each driving style, in combination with the corresponding road condition of each segment, the evaluation weight and the frequency weight of each road condition. The application realizes accurate evaluation of continuous, long-time and complex driving behavior, measures the risk of the driving behavior of a driver, and improves the objectivity and accuracy of driving behavior evaluation.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method for evaluating driving behavior, a computer program product, an apparatus, and a storage medium. Background Technology

[0002] The evaluation of a driver's driving behavior is often used as an important basis for assessing vehicle energy consumption, insurance coverage, and driving safety. This is especially true during driving, when drivers occasionally engage in aggressive driving behaviors such as sudden acceleration, abrupt braking, and frequent lane changes.

[0003] Existing driving behavior evaluation schemes use too few evaluation indicators, which cannot comprehensively and accurately reflect the user's driving behavior throughout the entire driving process. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides a method for evaluating driving behavior, a computer program product, an apparatus, and a storage medium.

[0005] Firstly, this application provides a method for evaluating driving behavior, including:

[0006] Acquire time-stamped driving data for the target vehicle;

[0007] The driving data is divided into multiple segments according to a preset time period, and road condition feature data and driving style feature data of each segment are statistically analyzed based on the driving data.

[0008] Based on the road condition feature data, the road condition, the frequency weight of the road condition, and the evaluation weight of the road condition are determined for each segment.

[0009] Based on the driving style feature data, the driving style corresponding to each segment is determined respectively;

[0010] Based on the preset base score corresponding to each driving style, combined with the road condition corresponding to each segment, the evaluation weight of each road condition, and the frequency weight, the driving behavior evaluation result of the target vehicle is obtained.

[0011] In one embodiment, determining the road condition, the frequency weight of the road condition, and the evaluation weight of the road condition for each segment based on the road condition feature data includes:

[0012] The road condition feature data of each segment is clustered as a sample point, and a first preset number of cluster centers are determined based on the clustering results, with each cluster center corresponding to a cluster.

[0013] Based on the clusters, the total number of segments, the number of segments in each cluster, and the average vehicle speed are calculated.

[0014] The road condition represented by each cluster is determined based on the average vehicle speed, and the road condition represented by the cluster is used as the road condition corresponding to each segment in the cluster.

[0015] Calculate the ratio of the number of segments to the number of segments for each type of road condition, and use it as the frequency weight of the corresponding road condition;

[0016] The evaluation weight for each road condition is determined based on the average vehicle speed.

[0017] In one embodiment, determining the driving style corresponding to each segment based on the driving style feature data includes:

[0018] The driving style feature data of each segment is clustered as a sample point, and a second preset number of cluster centers are determined based on the clustering results, with each cluster center corresponding to a cluster.

[0019] Based on the driving style feature data of the segments in the cluster, the driving style represented by the cluster is determined, and the driving style represented by the cluster is used as the driving style corresponding to each segment in the cluster.

[0020] In one embodiment, obtaining the driving behavior evaluation result of the target vehicle based on a preset base score corresponding to each driving style, combined with the road condition corresponding to each segment, the evaluation weight of each road condition, and the frequency weight, includes:

[0021] The score for each segment is obtained by multiplying the preset base score of the driving style corresponding to each segment with the evaluation weight of the corresponding road condition and the frequency weight.

[0022] The driving behavior score of the target vehicle is obtained by summing the scores.

[0023] Calculate the difference between the driving score and the preset base score for each driving style;

[0024] The driving style corresponding to the smallest difference is taken as the target driving style of the target vehicle.

[0025] In one embodiment, determining the evaluation weight for each road condition based on the average vehicle speed includes:

[0026] Based on the average vehicle speed, the evaluation weights for each road condition are determined using the analytic hierarchy process (AHP).

[0027] In one embodiment, before determining the road condition, the frequency weight of the road condition, and the evaluation weight of the road condition for each segment based on the road condition feature data, the method further includes: performing dimensionality reduction processing on the road condition feature data using principal component analysis.

[0028] And / or,

[0029] Before determining the driving style corresponding to each segment based on the driving style feature data, the method further includes:

[0030] Principal component analysis was used to reduce the dimensionality of the driving style feature data.

[0031] In one embodiment, the driving data includes vehicle speed, mileage traveled, and accelerator pedal opening signal;

[0032] The step of statistically analyzing road condition characteristic data and driving style characteristic data for each segment based on the driving data includes:

[0033] Based on the vehicle speed and the mileage traveled, the road condition characteristic data for each segment are statistically analyzed.

[0034] Based on the vehicle speed and the accelerator pedal opening signal, the driving style characteristic data for each segment are statistically analyzed.

[0035] Secondly, this application provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the method described in the first aspect.

[0036] Thirdly, this application provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described in the first aspect.

[0037] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the steps of the method described in the first aspect.

[0038] Based on common knowledge in the field, the above-mentioned preferred conditions can be combined arbitrarily to obtain various preferred embodiments of this application.

[0039] The aforementioned driving behavior evaluation methods, computer program products, devices, and storage media can achieve the following beneficial effects: by dividing driving data into multiple segments, statistically analyzing the road condition characteristic data and driving style characteristic data of each segment, and combining the preset base scores of different driving styles, the frequency weight of road conditions, and the evaluation weight, accurate assessment of continuous, long-term, and complex driving behaviors can be achieved to measure the risk of the driver's driving behavior, thereby improving the objectivity and accuracy of driving behavior assessment. This can provide objective and accurate data support for subsequent assessments of vehicle energy consumption economy, insurance amount, driving comfort, driving safety, and driving behavior. Attached Figure Description

[0040] Figure 1 This is a flowchart illustrating a method for evaluating driving behavior in one embodiment;

[0041] Figure 2 This is a schematic diagram of the modules of a driving behavior evaluation system in one embodiment;

[0042] Figure 3 This is a first internal structure diagram of a computer device in one embodiment;

[0043] Figure 4 This is a second internal structure diagram of a computer device in one embodiment. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0045] It should be noted that the illustrations provided in this embodiment are merely schematic representations of the basic concept of this application. The figures only show components relevant to this application and are not drawn according to the actual number, shape, and size of the components in implementation. In actual implementation, the form, quantity, and proportion of each component can be arbitrarily changed, and the component layout may also be more complex. The structures, proportions, sizes, etc., shown in the accompanying drawings are only used to complement the content disclosed in the specification for those skilled in the art to understand and read, and are not intended to limit the implementation conditions of this application. Therefore, they have no substantial technical significance. Any modification to the structure, change in the proportional relationship, or adjustment of the size, without affecting the effect and purpose that this application can produce, should still fall within the scope of the technical content disclosed in this application. At the same time, the terms such as "upper," "lower," "left," "right," "middle," and "one" used in this specification are only for clarity of description and are not intended to limit the scope of implementation of this application. Changes or adjustments in their relative relationships, without substantially altering the technical content, should also be considered within the scope of implementation of this application.

[0046] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the document does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0047] As illustrated herein, unless the context clearly indicates otherwise, words such as “a,” “an,” “an,” and / or “the” do not specifically refer to the singular and may also include the plural. Generally speaking, the terms “comprising” and “including” only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0048] The definitions used herein, such as the terms “having,” “may have,” “comprising,” or “may include,” indicate the presence of the corresponding function, operation, element, etc., and do not limit the presence of one or more other functions, operations, elements, etc. Furthermore, it should be understood that the terms “comprising” or “having” as used herein indicate the presence of the features, figures, steps, operations, elements, components, or combinations thereof described in the specification, without excluding the presence or addition of one or more other features, figures, steps, operations, elements, components, or combinations thereof.

[0049] The prefixes such as "first" and "second" used in this application embodiment are merely for distinguishing different descriptive objects and do not limit the position, order, priority, quantity, or content of the described objects. The use of ordinal numbers and other prefixes used to distinguish descriptive objects in this application embodiment does not constitute a limitation on the described objects. The description of the described objects is given in the claims or the context of the embodiments, and should not constitute unnecessary limitations due to the use of such prefixes. Furthermore, in the description of this embodiment, unless otherwise stated, "multiple" means two or more.

[0050] In one embodiment, such as Figure 1 As shown, the driving behavior evaluation method provided in this embodiment includes steps S101 to S105:

[0051] S101. Obtain time-stamped driving data of the target vehicle.

[0052] Among them, time-stamped driving data is actually a type of time-series data, which refers to a series of time-stamped related data recorded sequentially in time during the driving process of the target vehicle. This data covers a variety of information during the vehicle's driving process, such as vehicle speed, acceleration, braking status, steering wheel angle, engine speed, fuel consumption, mileage, geographical location (latitude and longitude), and various sensor readings of the vehicle at different times.

[0053] S102. Divide the driving data into multiple segments according to the preset time period, and statistically analyze the road condition characteristic data and driving style characteristic data of each segment based on the driving data.

[0054] In one embodiment, driving data includes vehicle speed and mileage. Accordingly, step S102 includes: calculating road condition characteristic data for each segment based on vehicle speed and mileage.

[0055] For example, based on vehicle speed, the maximum acceleration, maximum deceleration, acceleration time ratio, deceleration time ratio, constant speed time ratio, 0-20km / h speed ratio, 20-40km / h speed ratio, 40-60km / h speed ratio, 60-80km / h speed ratio, maximum speed, average speed, average speed excluding stopping time, speed standard deviation, acceleration standard deviation, average acceleration of the acceleration segment, average deceleration of the deceleration segment, acceleration standard deviation of the acceleration process, and deceleration standard deviation of the deceleration process can be calculated for each segment. Based on mileage, the travel distance of each segment can be calculated separately to serve as road condition feature data.

[0056] In one embodiment, the driving data also includes accelerator pedal information, such as an accelerator pedal opening signal, which can be used to determine the accelerator pedal position. Accordingly, step S102 further includes: calculating driving style characteristic data for each segment based on the vehicle speed and the accelerator pedal opening signal.

[0057] For example, based on vehicle speed, the rate of change of acceleration, the standard deviation of the rate of change of acceleration, and the average rate of change of acceleration can be calculated for each segment. Based on the accelerator pedal opening signal, the maximum accelerator pedal position, the average accelerator pedal position, the standard deviation of the accelerator pedal position, the maximum increase rate of the accelerator pedal position, the maximum decrease rate of the accelerator pedal position, the standard deviation of the rate of change of the accelerator pedal position, the average increase rate of the accelerator pedal position, the standard deviation of the increase rate of the accelerator pedal position, the average decrease rate of the accelerator pedal position, and the standard deviation of the decrease rate of the accelerator pedal position can be calculated for each segment, which can be used as driving style characteristic data.

[0058] Since the road condition feature data and driving style feature data of each segment include statistical data in multiple dimensions, dimensionality reduction processing is required to facilitate subsequent analysis. Specifically, in one embodiment, before step S103, the method of principal component analysis is used to reduce the dimensionality of the road condition feature data. In another embodiment, before step S104, the method of principal component analysis is used to reduce the dimensionality of the driving style feature data.

[0059] For example, principal component analysis is used to reduce the dimensionality of road condition feature data, including:

[0060] An initial matrix is ​​determined based on the road condition feature data of all segments. Each row of the initial matrix corresponds to a segment, and each column corresponds to a data dimension. If there are m segments and the road condition feature data includes statistical data across n dimensions, an m×n initial matrix can be obtained.

[0061] The initial matrix is ​​centered to obtain the first matrix. That is, the mean of each column is calculated first, and then the mean of the column in which each element of the initial matrix is ​​subtracted.

[0062] Then calculate the covariance matrix C of the first matrix:

[0063]

[0064] Where m is the number of segments, X is the first matrix, and X T It is the transpose of the first matrix.

[0065] Perform eigenvalue decomposition on the covariance matrix C to obtain the eigenvalues ​​of the covariance matrix C and the eigenvectors corresponding to each eigenvalue.

[0066] Arrange the corresponding eigenvectors in descending order from left to right into a matrix, and take the first k columns to form the second matrix.

[0067] Based on the first matrix X and the second matrix W, the third matrix Y, after being reduced to m×k dimensions, is calculated:

[0068] Y = XW

[0069] Among them, the eigenvectors corresponding to the eigenvalues ​​are the principal components.

[0070] Sort the corresponding eigenvectors from left to right according to the eigenvalues ​​from largest to smallest, calculate the contribution rate of each eigenvalue, and the contribution rate of each eigenvalue is equal to the eigenvalue divided by the sum of all eigenvalues. By gradually summing the contribution rates from left to right, the cumulative contribution rate of each principal component can be obtained.

[0071] Finally, the first *a* principal components are selected and retained to obtain the dimensionality-reduced target matrix, where *a* is determined based on a preset cumulative contribution rate threshold. For example, if the cumulative contribution rates are 40%, 70%, 90%, 95%, and 100% respectively, and the threshold is set to 90%, then the first three principal components are selected.

[0072] Similarly, an initial matrix can be generated based on the driving style feature data of all segments. The dimensionality reduction process is the same as that used in principal component analysis to reduce the dimensionality of road condition feature data, and will not be elaborated here.

[0073] S103. Based on the road condition feature data, determine the road condition, the frequency weight of the road condition, and the evaluation weight of the road condition for each segment.

[0074] In one embodiment, step S103 includes steps S1031 to S1035:

[0075] S1031. Cluster the road condition feature data of multiple segments, and determine a first preset number of cluster centers based on the clustering results, with each cluster center corresponding to a cluster.

[0076] S1032. Based on clustering, count the total number of segments, the number of segments in each cluster, and the average vehicle speed;

[0077] S1033. Determine the road condition represented by each cluster based on the average vehicle speed, and use the road condition represented by the cluster as the road condition corresponding to each segment in the cluster.

[0078] S1034. Calculate the ratio of the number of segments to the number of segments for each road condition, and use it as the frequency weight of the corresponding road condition.

[0079] S1035. Determine the evaluation weight for each road condition based on the average vehicle speed.

[0080] For example, step S1031 includes:

[0081] (1) Treat the road condition feature data of each segment as a sample point;

[0082] (2) Randomly select 4 sample points from a number of sample points as the initial cluster centers;

[0083] (3) Calculate the distance from each sample point to the initial cluster center, and form a cluster by combining each sample point with the nearest cluster center, thus forming 4 clusters;

[0084] (4) Calculate the mean position of the sample points in each cluster and use the mean position as the new cluster center, thus obtaining 4 new cluster centers;

[0085] (5) Repeat steps (3) and (4) until all cluster centers no longer change. Each sample point forms a cluster with the nearest cluster center, that is, four clusters C1, C2, C3 and C4 are finally formed.

[0086] In step S1032, based on the above clusters, the total number of segments and the number of segments in each cluster can be counted, and the average speed of the cluster can be obtained based on the average speed of the segments in each cluster.

[0087] In step S1033, based on the average vehicle speed, the road conditions represented by the four clusters are determined to be congested, low speed, medium speed and high speed, respectively. The road condition corresponding to each segment is determined by the road condition represented by the cluster to which it belongs.

[0088] In step S1034, if the number of segments in clusters C1 to C4 are 937, 754, 543 and 1436 respectively, the ratio of the number of segments to the total number of segments 3670 can be calculated, and then the frequency weights of congestion, low speed, medium speed and high speed are obtained as 25.531%, 20.545%, 14.796% and 39.128% respectively.

[0089] The higher the vehicle speed, the greater the probability of traffic accidents and the higher the mortality rate. Therefore, in step S1035, the risk of different road conditions can be quantified based on the average vehicle speed using the analytic hierarchy process (AHP). That is, in one embodiment, step S105 includes: determining the evaluation weight of each road condition based on the average vehicle speed using the AHP.

[0090] For example, based on the above, the average speed of each road condition is compared pairwise to determine their relative risk. A 1-9 scale is used, that is, the relative risk between two factors is represented by a number between 1 and 9, as shown in Table 1.

[0091] Table 11-9 Scaling Method

[0092] Equally important 1 Slightly more important 3 More importantly 5 More importantly 7 Extremely important 9 The median value of adjacent judgment 2，4，6，8

[0093] For example, comparing the average speeds of "congestion" and "low speed," "low speed" carries a greater risk than "congestion." This might result in a risk score of 3 for "low speed" and 1 for "congestion." Consequently, the risk ratio of "congestion" to "low speed" is 1:3, and the risk ratio of "low speed" to "congestion" is 3:1.

[0094] Based on this logic, a discrimination matrix can be generated according to the average vehicle speed and the 1-9 scale method, as shown in Table 2.

[0095] Table 2 Discriminant Matrix

[0096]

[0097] After obtaining the discriminant matrix, a consistency check is needed to ensure its consistency. Given that the dimension N of the discriminant matrix is ​​4, calculate the consistency index CI:

[0098]

[0099] Where, ∈ max It is the largest eigenvalue of the discrimination matrix.

[0100] Due to consistency ratio When CR is less than 0.1, the discriminant matrix is ​​considered to have satisfactory consistency; otherwise, the discriminant matrix is ​​adjusted until the consistency check is met.

[0101] After the discriminant matrix satisfies the consistency check, the eigenvector of the discriminant matrix is ​​calculated, and then the eigenvector is normalized so that the sum of its elements is 1. The evaluation weights of congestion, low speed, medium speed and high speed are approximately 0.0662+0.1497+0.2399+0.5443, respectively.

[0102] For example, first calculate the sum of each column of the discrimination matrix, that is, add up each column of the discrimination matrix to get:

[0103] The sum of congestion levels = 1 + 3 + 4 + 6 = 14;

[0104] The sum of the low-speed columns = 1 / 3 + 1 + 2 + 4 = 7.333;

[0105] Medium speed column sum=1 / 4+1 / 2+1+3=4.75;

[0106] The sum of the high-speed train values ​​is 1 / 6 + 1 / 4 + 1 / 3 + 1 = 1.75.

[0107] Then, the discrimination matrix is ​​normalized by calculating the sum of the values ​​of each element in the discrimination matrix divided by the sum of the values ​​of its columns. The normalization results are shown in Table 3.

[0108] Table 3 Normalization results of the discriminant matrix

[0109]

[0110] Adding each row of the normalized discriminant matrix together and then dividing by 4 (the dimension of the discriminant matrix) yields the following:

[0111] (0.0714+0.0455+0.0526+0.0952) / 4≈0.0662;

[0112] (0.2143+0.1364+0.1053+0.1429) / 4≈0.1497;

[0113] (0.2857+0.2727+0.2105+0.1905) / 4≈0.2399;

[0114] (0.4286+0.5455+0.6316+0.5714) / 4≈0.5443.

[0115] Therefore, the final calculated evaluation weights are 0.0662 for congestion, 0.1497 for low speed, 0.2399 for medium speed, and 0.5443 for high speed.

[0116] S104. Based on the driving style characteristic data, determine the driving style corresponding to each segment.

[0117] In one embodiment, step S104 includes:

[0118] S1041. Cluster the driving style feature data of each segment as a sample point, and determine a second preset number of cluster centers based on the clustering results. Each cluster center corresponds to a cluster.

[0119] S1042. Based on the driving style feature data of the segments in the cluster, determine the driving style represented by the cluster, and use the driving style represented by the cluster as the driving style corresponding to each segment in the cluster.

[0120] For example, step S1041 includes:

[0121] (6) Take the driving style feature data of each segment as a sample point;

[0122] (7) Randomly select 3 sample points from a number of sample points as the initial cluster centers;

[0123] (8) Calculate the distance from each sample point to the initial cluster center, and form a cluster by combining each sample point with the nearest cluster center, thus forming 3 clusters;

[0124] (9) Calculate the mean position of the sample points in each cluster and use the mean position as the new cluster center, thus obtaining 3 new cluster centers;

[0125] (10) Repeat steps (3) and (4) until all cluster centers no longer change. Each sample point forms a cluster with the nearest cluster center, that is, three clusters D1, D2 and D3 are finally formed.

[0126] Since driving style feature data also includes statistical data in multiple dimensions, in step S1042, the statistical data of the same dimension of segments in different clusters can be compared, and finally the driving styles represented by the three clusters are determined to be conservative, traditional and aggressive.

[0127] For example, the reduced-dimensional driving style feature data includes the standard deviation of the accelerator pedal position for this segment. The larger the standard deviation of the accelerator pedal position, the more frequent or unstable the pedal position changes. The smaller the standard deviation of the accelerator pedal position, the smoother the pedal position changes.

[0128] The average of the standard deviations of the accelerator pedal position in the three clusters can be calculated separately. The cluster with the smallest average is identified as conservative, the cluster with the largest average is identified as radical, and the remaining clusters are identified as conventional.

[0129] S105. Based on the preset base score corresponding to each driving style, combined with the road conditions corresponding to each segment, the evaluation weight and frequency weight of each road condition, the driving behavior evaluation result of the target vehicle is obtained.

[0130] In one embodiment, step S105 includes:

[0131] S1051. Calculate the product of the preset base score of the driving style corresponding to each segment, the evaluation weight of the corresponding road condition, and the frequency weight to obtain the score of each segment.

[0132] S1052. Calculate the sum of the scores to obtain the driving behavior score of the target vehicle.

[0133] For example, there are J segments in total, and the preset base score for the road condition of the i-th segment is denoted as L. i The traffic frequency weight of the i-th segment is f. i The road condition evaluation weight for the i-th segment is w. i The driving behavior score G of the target vehicle can then be calculated.

[0134]

[0135] After obtaining the driving behavior score of the target vehicle, the closest driving style can be determined based on the specific score of the driving behavior score.

[0136] In another embodiment, after step S1052, the method further includes:

[0137] S1053. Calculate the difference between the driving score and the preset base score for each driving style;

[0138] S1054. The driving style with the smallest difference is taken as the target driving style of the target vehicle.

[0139] For example, assuming the conservative preset base score is 85 points, the traditional preset base score is 75 points, and the aggressive preset base score is 65 points, the calculated driving behavior score is 70 points, which is the smallest difference from the traditional preset base score. Therefore, the target driving style is traditional.

[0140] It should be understood that, although Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise explicitly stated herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0141] To implement the above-described method for evaluating driving behavior, this application also provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the method described above.

[0142] In one embodiment, this computer program product presents itself as a driving behavior evaluation system. For example... Figure 2 As shown, the driving behavior evaluation system includes the following modules:

[0143] The data acquisition module 201 is used to acquire time-stamped driving data of the target vehicle;

[0144] The feature determination module 202 is used to divide the driving data into multiple segments according to a preset time period, and to statistically analyze the road condition feature data and driving style feature data of each segment based on the driving data.

[0145] The road condition analysis module 203 is used to determine the road condition, the frequency weight of the road condition, and the evaluation weight of the road condition for each segment based on the road condition feature data.

[0146] The driving style analysis module 204 is used to determine the driving style corresponding to each segment based on the driving style feature data.

[0147] The evaluation module 205 is used to obtain the driving behavior evaluation result of the target vehicle based on the preset base score corresponding to each driving style, combined with the road conditions corresponding to each segment, the evaluation weight of each road condition, and the frequency weight.

[0148] Specific limitations regarding the driving behavior evaluation system can be found in the limitations of the driving behavior evaluation methods described above, and will not be repeated here. Each module in the aforementioned driving behavior evaluation system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0149] This application also provides a computer device. In one embodiment, the computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the driving behavior evaluation method described in the above embodiment.

[0150] In one embodiment, the computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores relevant data for evaluating driving behavior. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a method for evaluating driving behavior.

[0151] In one embodiment, the computer device may be a terminal, and its internal structure diagram may be as follows: Figure 4As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for evaluating driving behavior. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0152] Those skilled in the art will understand that Figure 3 and Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0153] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the driving behavior evaluation method in the above embodiments.

[0154] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0155] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0156] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method of evaluating driving behavior, characterized by, The evaluation methods include: Acquire time-stamped driving data for the target vehicle; The driving data is divided into multiple segments according to a preset time period, and road condition feature data and driving style feature data of each segment are statistically analyzed based on the driving data. The road condition feature data of each segment is treated as a sample point and clustered. A first preset number of cluster centers are determined based on the clustering results, and each cluster center corresponds to a cluster. Based on the clusters, the total number of segments, the number of segments in each cluster, and the average vehicle speed are counted. The road condition represented by each cluster is determined based on the average vehicle speed, and the road condition represented by the cluster is used as the road condition corresponding to each segment in the cluster. The ratio of the number of segments to the total number of segments for each type of road condition is calculated as the frequency weight of the corresponding road condition. The evaluation weight of each type of road condition is determined based on the average vehicle speed. Based on the driving style feature data, the driving style corresponding to each segment is determined respectively; Calculate the product of the preset base score of the driving style corresponding to each segment, the evaluation weight of the corresponding road condition, and the frequency weight to obtain the score of each segment; calculate the sum of the scores to obtain the driving behavior score of the target vehicle; calculate the difference between the driving behavior score and the preset base score of each driving style; and select the driving style with the smallest difference as the target driving style of the target vehicle.

2. The evaluation method according to claim 1, characterized by, The step of determining the driving style corresponding to each segment based on the driving style feature data includes: The driving style feature data of each segment is clustered as a sample point, and a second preset number of cluster centers are determined based on the clustering results, with each cluster center corresponding to a cluster. Based on the driving style feature data of the segments in the cluster, the driving style represented by the cluster is determined, and the driving style represented by the cluster is used as the driving style corresponding to each segment in the cluster.

3. The evaluation method according to claim 1, wherein The step of determining the evaluation weight for each road condition based on the average vehicle speed includes: Based on the average vehicle speed, the evaluation weights for each road condition are determined using the analytic hierarchy process (AHP).

4. The evaluation method as described in claim 1, characterized in that, Before determining the road condition, frequency weight, and evaluation weight of each segment based on the road condition feature data, the method further includes: performing dimensionality reduction processing on the road condition feature data using principal component analysis. And / or, Before determining the driving style corresponding to each segment based on the driving style feature data, the method further includes: Principal component analysis was used to reduce the dimensionality of the driving style feature data.

5. The evaluation method according to claim 1, wherein The driving data includes vehicle speed, mileage, and accelerator pedal opening signal; The step of statistically analyzing road condition characteristic data and driving style characteristic data for each segment based on the driving data includes: Based on the vehicle speed and the mileage traveled, the road condition characteristic data for each segment are statistically analyzed. Based on the vehicle speed and the accelerator pedal opening signal, the driving style characteristic data for each segment are statistically analyzed.

6. A computer program product comprising computer programs / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1-5.

7. A computer device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1-5.

8. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method described in any one of claims 1-5.

Images